|Publication number||US7634147 B2|
|Application number||US 11/930,801|
|Publication date||Dec 15, 2009|
|Filing date||Oct 31, 2007|
|Priority date||Mar 25, 2004|
|Also published as||US7336841, US8023757, US20050213826, US20080123980, US20100061590|
|Publication number||11930801, 930801, US 7634147 B2, US 7634147B2, US-B2-7634147, US7634147 B2, US7634147B2|
|Original Assignee||Intel Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (8), Non-Patent Citations (3), Referenced by (19), Classifications (8), Legal Events (1)|
|External Links: USPTO, USPTO Assignment, Espacenet|
This application is a Continuation of U.S. application Ser. No. 10/808,981, filed Mar. 25, 2004 now U.S. Pat. No. 7,336,841, which is incorporated herein by reference.
The present invention relates generally to systems for rights management for digital video, and more particularly to fingerprinting digital video transmitted over networks.
A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure as it appears in the Patent and Trademark Office patent file or records, but otherwise reserves all copyright rights whatsoever. The following notice applies to the software and data as described below and in the drawings hereto: Copyright© 2003, 2004 Intel Corporation. All Rights Reserved.
With the rapid growth of networking infrastructure and bandwidth capabilities, the volume of digital media traffic transmitted over distribution channels such as public and private networks has climbed dramatically. More and more digital content is produced and consumed in home networks, broadcast networks, enterprise networks etc. However, the growth of digital media traffic has come with a corresponding growth in the digital piracy rate. As a result, there is a need by many broadcast network operators and other digital rights owners for copyright protection and enforcement mechanisms for media transmitted over various distribution channels.
In the following detailed description of exemplary embodiments of the invention, reference is made to the accompanying drawings that form a part hereof, and in which is shown by way of illustration specific exemplary embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the various embodiments of the invention, and it is to be understood that other embodiments may be utilized and that logical, mechanical, electrical and other changes may be made without departing from the scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense.
In the Figures, the same reference number is used throughout to refer to an identical component which appears in multiple Figures. Signals and connections may be referred to by the same reference number or label, and the actual meaning will be clear from its use in the context of the description.
In some embodiments of the invention, operating environment 100 comprises a video server 110 and a video receiver 102 communicably coupled via a channel 120. Video server 110 may be any type of system capable of storing and transmitting video data to one or more video receivers 102 through channel 120.
Channel 120 may be any channel that may send and received video data and data associated with the video data. Examples of such channels include public and private networks (both wired and wireless), the Internet, and broadcast channels such as cable television networks and satellite distribution networks. Channel 120 may comprise multiple media, and transmission and reception need not occur over the same media. For example, in the case of satellite distribution networks, video data may be transmitted by satellite, while other data may be received through a different media such as a telephone or network channel.
Video receiver 102 may be any system capable of receiving video data and transmitting fingerprint data to a verification module 112. For example, video receiver 120 may be a personal computer, a laptop computer, or a set-top box capable of receiving video data. Video receiver 102 includes a fingerprint generation module 106 capable of generating a fingerprint from a video data stream transmitted to video receiver 102. In some embodiments, the generated fingerprint may be transmitted to a fingerprint verification module 112.
Verification module 112 may be a module incorporated on video server 110, or it may be incorporated on a separate computing system from video server 110 that is also communicably coupled to channel 120. The fingerprint verification module 112 compares the fingerprint generated by video receiver 102 with a reference fingerprint for the video data stream that may be archived in fingerprint mismatch database 114.
Further details on the operation of embodiments of the invention are provided below with reference to
The software components running in the operating environment 100 may be read from a machine-readable media and run under the control of an operating system, and interfaced with the operating system. Examples of such machine-readable media include hard disks, floppy disks, CD-ROMs, DVD-ROMs. Further, machine-readable media includes wired and wireless signals transmitted over a network.
Additionally, in varying embodiments the systems and methods of the present invention may be implemented in firmware.
Next, the system selects a subset of image frames from the video data (block 204). In some embodiments, the subset is selected on the basis of control codes embedded in the video data. In these embodiments, the control codes are typically created and embedded in the video data when a reference fingerprint is generated for the video data stream. The reference fingerprint comprises a fingerprint of the video data generated prior to its distribution to video receivers in order to be used by a fingerprint verification module for comparison purposes. Candidates for inclusion in the subset typically comprise intra macro-blocks (I-Frames) in an MPEG video data stream. Additional selection criteria may also be used, for example a percentage of candidate frames may be used to reduce the size of the subset.
For each frame in the selected subset, the system generates sub-fingerprints (block 206). These sub-fingerprints are generated based on the pixel data in the image frame. Further details on a method for generating sub-fingerprints are provided below with reference to
Next, the generated sub-fingerprints are assembled into a data structure that comprises a fingerprint for the video data stream (block 208). The fingerprint may then be transmitted to a verification server (block 210).
The verification server then compares the generated fingerprint with a reference fingerprint (block 212). The comparison may be used to determine copyrighted video data has been played on a receiver. Additionally, the comparison may determine if the video source has been altered, as alteration will result in a different fingerprint. Further, the location of the alteration may be determined based on the fingerprint and the sub-fingerprints within the fingerprint. For example, a video data stream containing an advertisement may be distributed through a channel. Along the distribution channel, an intermediate party may substitute the original advertisement with a different advertisement. As result, the sub-fingerprints for the substituted advertisement will be different, indicating that the original video data has been altered and where the alteration occurred.
The method begins by computing a Discrete Cosine Transform (DCT) for a pixel block in an image frame comprising a pixel matrix. In some embodiments, the DCT is calculated for the luminance value of the pixels. Various methods for calculating a DCT are known in the art. In some embodiments, an 8×8 DCT size block is used. However, the invention is not limited to any particular block size for the DCT. For example, a 16×16 block may be used in alternative embodiments. The choice of a particular block size may, at least in part, be determined by performance considerations. For example, a 16×16 DCT is more expensive in terms of performance. Additionally, accelerators are available for 8×8 DCT blocks.
Additionally, those of skill in the art will appreciate that other transformation algorithms besides DCT could be substituted for the DCT transformation and are within the scope of the invention. For example, a weighted wavelet transformation as is known in the art may be used. The choice of transformation may be influenced by the availability of accelerators for the desired transformation and the degree to which the selected transformation is used in other aspects of video processing.
Next, a variance of the DCT coefficients is calculated (block 224). The variance value is then placed in a variance matrix having the same size as the pixel matrix. The variance value is placed in the same position in the variance matrix as the pixel value of the pixel matrix that is the subject of the DCT calculation. Thus, in effect, the luminance pixel value in the pixel matrix is replaced by the variance value in the variance matrix.
Next, the minimum of the variance values in each of a plurality of signature windows is determined (block 228). The variance matrix is segmented into a plurality of signature windows. In some embodiments, the signature window size is 8×8. However, the invention is not limited to any particular size for the signature window. In each signature window, the minimum variance value is determined. The position in the variance matrix having the minimum variance value is marked with a predetermined value in a corresponding position in a constellation matrix having the same size as the variance matrix. Other positions in the signature window that are not the minimum are marked with a different predetermined value. In some embodiments, the minimum value is marked with a “1” (one), while the other positions are marked with a “0” (zero). As a result, the 1's in the constellation matrix represent the parts of the video with most steady visual properties. The distribution of this steadiness represents a signature.
Next, the constellation matrix is encoded into a sub-fingerprint 240 and a positional indicator is set indicating the position of the sub-fingerprint in the video data (block 232). In some embodiments, run-length encoding is used to code the constellation matrix. However, alternative methods of coding are known in the art and may be used instead of, or in addition to, run-length encoding. Further, in some embodiments, the positional indicator is a time code. However, in alternative embodiments, the positional indicator may be a byte offset in the video data stream.
In some embodiments, the architecture 400 includes a user interface layer 402, an application layer 404, a virtual machine layer 406, and a hardware layer 408.
The UI layer 402 listens to client requests and brokers the distribution of client requests to the layer below it. Below the UI layer 402 is the application layer 404. This layer manages the application state and flow-graph, but is typically resource status unaware. Underneath the application layer 404 is the virtual machine layer 406 for resource management and component parameterization. At the lowest layer is the hardware layer 408. The hardware layer typically includes the drivers and the operating system controlling the video receiver. Each layer has an array of components through which data or control is streamed.
In some embodiments, the hardware layer 408 includes a transport infrastructure. The transport infrastructure includes a NIM (Network Interface Module) 410, which extracts the transport packets comprising video data, and a TD (transport de-multiplexor) 412 which de-multiplexes audio and video packetized elementary streams. An MPD (Mpeg Decoder) 414 decompresses the video and parks the uncompressed video in a virtual storyboard with decompression metadata in a TS (Transport Stream) 416. A temporary workspace manager forwards frames to a fingerprint generator 420. Pre-processor 422 pushes the processing data through the fingerprint processing pipeline, which includes DCT module 424, variance module 426, and constellation module 428 that execute the methods described above with respect to
Systems and methods for generating fingerprint data for video data have been described. The systems and methods of various embodiments provide advantages over previous systems. For example, in some embodiments, the overhead due to fingerprinting, is estimated to be less than 1% (assuming DCT computation is offloaded). Additionally, management overhead to control fingerprinting in some embodiments (control codes and signature PDU) is estimated to increase the bit-rate by less than 0.0001%. As an example, for an hour-long program segment, fingerprint block size is estimated to be approximately 64 kbits (256*256). Additionally, the systems and methods of the embodiments of the invention typically fit with existing video infrastructure with relatively minor alteration.
Although specific embodiments have been illustrated and described herein, it will be appreciated by those of ordinary skill in the art that any arrangement which is calculated to achieve the same purpose may be substituted for the specific embodiments shown. This application is intended to cover any adaptations or variations of the present invention.
The terminology used in this application is meant to include all of these environments. It is to be understood that the above description is intended to be illustrative, and not restrictive. Many other embodiments will be apparent to those of skill in the art upon reviewing the above description. Therefore, it is manifestly intended that this invention be limited only by the following claims and equivalents thereof.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US6597802 *||Aug 25, 1999||Jul 22, 2003||International Business Machines Corp.||System and method for generating a rolled surface representation from a set of partial images|
|US7194115||Jul 26, 2001||Mar 20, 2007||Nec Corporation||Fingerprint identification method and apparatus|
|US7194116||Aug 25, 2004||Mar 20, 2007||Sony Corporation||Fingerprint image reconstruction based on motion estimate across a narrow fingerprint sensor|
|US7197168||Jul 12, 2002||Mar 27, 2007||Atrua Technologies, Inc.||Method and system for biometric image assembly from multiple partial biometric frame scans|
|US7212658||Aug 25, 2004||May 1, 2007||Sony Corporation||System for fingerprint image reconstruction based on motion estimate across a narrow fingerprint sensor|
|US7251372 *||Jan 14, 2004||Jul 31, 2007||Nec Solutions (America) Inc.||Method and system for compressing digitized fingerprint images by a uniform degree of compression|
|US7336841||Mar 25, 2004||Feb 26, 2008||Intel Corporation||Fingerprinting digital video for rights management in networks|
|US20050213826||Mar 25, 2004||Sep 29, 2005||Intel Corporation||Fingerprinting digital video for rights management in networks|
|1||"U.S. Appl. No. 10/808,981, Non-Final Office Action mailed Jun. 6, 2007", 7 pgs.|
|2||"U.S. Appl. No. 10/808,981, Notice of Allowance mailed Sep. 20, 2007", 3 pgs.|
|3||"U.S. Appl. No. 10/808,981, Response filed Aug. 31, 2007 Non-Final Office Action mailed Jun. 6, 2007", 10 pgs.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US8023757||Sep 20, 2011||Intel Corporation||Fingerprinting digital video for rights management in networks|
|US8340343 *||Oct 31, 2008||Dec 25, 2012||General Instrument Corporation||Adaptive video fingerprinting|
|US8488835||May 21, 2008||Jul 16, 2013||Yuvad Technologies Co., Ltd.||System for extracting a fingerprint data from video/audio signals|
|US8498487 *||Oct 31, 2008||Jul 30, 2013||Sri International||Content-based matching of videos using local spatio-temporal fingerprints|
|US8538069 *||Dec 18, 2012||Sep 17, 2013||General Instrument Corporation||Adaptive video fingerprinting|
|US8548192 *||May 22, 2008||Oct 1, 2013||Yuvad Technologies Co., Ltd.||Method for extracting a fingerprint data from video/audio signals|
|US8577077||May 22, 2008||Nov 5, 2013||Yuvad Technologies Co., Ltd.||System for identifying motion video/audio content|
|US8611701||May 21, 2008||Dec 17, 2013||Yuvad Technologies Co., Ltd.||System for facilitating the search of video content|
|US8756249 *||Aug 23, 2011||Jun 17, 2014||Emc Corporation||Method and apparatus for efficiently searching data in a storage system|
|US8825626 *||Aug 23, 2011||Sep 2, 2014||Emc Corporation||Method and system for detecting unwanted content of files|
|US20100049711 *||Oct 31, 2008||Feb 25, 2010||Gajinder Singh||Content-based matching of videos using local spatio-temporal fingerprints|
|US20100061590 *||Mar 11, 2010||Raja Neogi||Fingerprinting digital video for rights management in networks|
|US20100066759 *||May 21, 2008||Mar 18, 2010||Ji Zhang||System for Extracting a Fingerprint Data From Video/Audio Signals|
|US20100111352 *||Oct 31, 2008||May 6, 2010||General Instrument Corporation||Adaptive video fingerprinting|
|US20100135521 *||May 22, 2008||Jun 3, 2010||Ji Zhang||Method for Extracting a Fingerprint Data From Video/Audio Signals|
|US20100169911 *||May 26, 2008||Jul 1, 2010||Ji Zhang||System for Automatically Monitoring Viewing Activities of Television Signals|
|US20100215210 *||May 21, 2008||Aug 26, 2010||Ji Zhang||Method for Facilitating the Archiving of Video Content|
|US20100215211 *||May 21, 2008||Aug 26, 2010||Ji Zhang||System for Facilitating the Archiving of Video Content|
|US20100265390 *||May 21, 2008||Oct 21, 2010||Ji Zhang||System for Facilitating the Search of Video Content|
|International Classification||G09G1/06, G06K9/36, G06K9/00|
|Cooperative Classification||G06K9/00711, H04N19/467|
|European Classification||G06K9/00V3, H04N7/26E10|